检索结果-内蒙古大学图书馆

international Conference on signal Processing and Communication (iCsC)

作者： Abhijeet sanjiv Bonde Pradeep Narwade s. V. Bonde Computer Science & Engineering Jaypee Institute of Information Technology Noida UP India Electronics & Telecommunication Engg. S.G.G.S.I.E. & T. Nanded Maharashtra India

ISBN: (纸本)9781665454315

Offline signature verification is an important and critical task in biometrics as signature shape is varying with time. We are proposing a novel approach for offline signature verification using the histogram of Gaussian Weighting Based tangent Angle (GWBtA). As signatures differentiated using shapes, so shape features are playing an important role in offline signature verification. Here the distribution of the pixels around the center pixel of the block is encoded to GWBtA. While computing GWBtA, the coordinates of the pixels are transformed to give more importance to the pixels which are nearer to the center pixels by using Gaussian weighting. the distances between histograms of GWBtA of signatures are utilized to classify the signature. the results show that the GWBtA gives more accurate results than existing tangent angle.

关键词： support vector machines Handwriting recognition Histograms shape Biometrics (access control) signal processing task analysis

来源：评论

学校读者我要写书评

暂无评论

Mitigating transformer Overconfidence via Lipschitz Regularization

arXiv

引用

arXiv 2023年

作者： Ye, Wenqian Ma, Yunsheng Cao, Xu tang, Kun Department of Computer Science University of Virginia CharlottesvilleVA United States College of Engineering Purdue University West LafayetteIN United States Department of Computer Science University of Illinois Urbana-Champaign UrbanaIL United States AI Lab Shenzhen Children's Hospital Shenzhen China T Lab Tencent Beijing China

though transformers have achieved promising results in many computer vision tasks, they tend to be over-confident in predictions, as the standard Dot Product self-Attention (DPsA) can barely preserve distance for the unbounded input domain. in this work, we fill this gap by proposing a novel Lipschitz Regularized transformer (LRFormer). specifically, we present a new similarity function with the distance within Banach space to ensure the Lipschitzness and also regularize the term by a contractive Lipschitz Bound. the proposed method is analyzed with a theoretical guarantee, providing a rigorous basis for its effectiveness and reliability. Extensive experiments conducted on standard vision benchmarks demonstrate that our method outperforms state-of-the-art single forward pass approaches in prediction, calibration, and uncertainty estimation. © 2023, CC BY.

关键词： Banach spaces

来源：评论

学校读者我要写书评

暂无评论

Reduced plaintext for ciphers (RPC) algorithm

引用

AiP Conference Proceedings 2024年第1期2802卷

作者： U. thirupalu A. Rajasekhar Reddy P. Chandrakanth Dept. of Computer Science and Engineering Audisankara College of Engineering & Technology Gudur Andhra Pradesh India Dept. of Computer Science and Engineering N.B.K.R.I.S.T Vidyanagar Andhra Pradesh India

in Cryptosystem, the cipher text plays an important role for protecting, storing and transmitting through different medium. still today most of the algorithms like DEs, AEs, RC family, RsA etc. produced cipher text is equal size or greater than the actual size of plaintext. so that these cipher text occupies more memory space, took more time by transmitting over the internet and this is a prone to break the cipher text. if we reduce the size of the plaintext, relatively the size of cipher text is reduced and also the storage and transmitting rate is minimized. to reduce the size, storage and transmitting rate, i introduce a new algorithm that is Reduced Plaintext Cipher (RPC) Algorithm. through this algorithm, the plaintext is reduced relatively the cipher text is also reduced. so that the cipher text size is small, occupies less memory, and transmitting rate is high and also it difficult to break by the cryptanalysts because the reduced text is as an intermediate code between actual plaintext and generated cipher text.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning

arXiv

引用

arXiv 2024年

作者： Chen, Jinyin Mu, Wenbo Zhang, Luxin Huang, Guohan Zheng, Haibin Cheng, Yao The Institute of Cyberspace Security The College of Information Engineering Zhejiang University of Technology Hangzhou310023 China The College of Information Engineering Zhejiang University of Technology Hangzhou310023 China National Key Laboratory of Electromagnetic Space Security Jiaxing China The College of Computer Science and Technology The Institute of Cyberspace Security Zhejiang University of Technology Hangzhou310023 China The Digital Service TÜV SÜD Asia Pacific Pte. Ltd. 609937 Singapore

Graph neural network (GNN) has captured wide attention due to its capability of graph representation learning for graph-structured data. However, the distributed data silos limit the performance of GNN. Vertical federated learning (VFL), an emerging technique to process distributed data, successfully makes GNN possible to handle the distributed graph-structured data. Despite the prosperous development of vertical federated graph learning (VFGL), the robustness of VFGL against the adversarial attack has not been explored yet. Although numerous adversarial attacks against centralized GNNs are proposed, their attack performance is challenged in the VFGL scenario. to the best of our knowledge, this is the first work to explore the adversarial attack against VFGL. A query-efficient hybrid adversarial attack framework is proposed to significantly improve the centralized adversarial attacks against VFGL, denoted as NA2, short for Neuron-based Adversarial Attack. specifically, a malicious client manipulates its local training data to improve its contribution in a stealthy fashion. then a shadow model is established based on the manipulated data to simulate the behavior of the server model in VFGL. As a result, the shadow model can improve the attack success rate of various centralized attacks with a few queries. Extensive experiments on five real-world benchmarks demonstrate that NA2 improves the performance of the centralized adversarial attacks against VFGL, achieving state-of-the-art performance even under potential adaptive defense where the defender knows the attack method. Additionally, we provide interpretable experiments of the effectiveness of NA2 via sensitive neurons identification and visualization of t-sNE. the code and datasets are available at https://***/hgh0545/NA2. Copyright © 2024, the Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

the role of cloud computing technology: A savior to fight the lockdown in COViD 19 crisis, the benefits, characteristics and applications

引用

international Journal of intelligent Networks 2021年 2卷 166-174页

作者： Alhomdy, sharaf thabit, Fursan Abdulrazzak, Fua'ad Hasan Haldorai, Anandakumar Jagtap, sudhir Professor. Emirates International University-Yemen Ph.D Researcher. School of Computational Sciences S.R.T.M. University Nanded India Associated Professor. Department of Communication Technology and Networks Thamar University Yemen Associated Professor. Department of Computer Science and Engineering Sri Eshwar College of Engineering Tamil Nadu Coimbatore India Professor and Principle of Swami Vivekanand Campus India

the contagion of the Coronavirus (COViD-19) led to a global lockdown that put governments in emergency mode. With the total number of positive cases worldwide exceeding the 97.46 million mark, social distancing appears to be the only effective strategy to contain the virus at the moment. As a result, companies face obstacles and find it difficult to respond to this current challenge of remote working. the impact of the novel COViD-19 has created many new challenges, and many of us have had to adopt new ways of working. With the need for accessing to critical applications and the scalability of the infrastructure, cloud computing is emerging as an underlying technology. the cloud technology had a major role in fighting the epidemic;it becomes a salvation for governments and organizations in numerous fields of life, education, health, industry, communication, remote surveillance, and more information. therefore, this study presents the benefits, characteristics and applications of cloud computing and explains how the cloud contributes to improving life in all regions of the world during COViD-19. it shows that the cloud computing helps countries in combating COViD 19, in education and health sectors, also in the economic and commercial aspects. it investigates the current state by distributing an online questionnaire to various people of academic and non-academic backgrounds in different places over the world in the iCt and education sectors. the results showed that there is an effective role for cloud computing during the epidemic. © 2021 the Author(s)

关键词： COViD-19

来源：评论

学校读者我要写书评

暂无评论

Digital twin-Assisted space-Air-Ground integrated Multi-Access Edge Computing for Low-Altitude Economy: An Online Decentralized Optimization Approach

arXiv

引用

arXiv 2024年

作者： He, Long sun, Geng sun, Zemin Wang, Jiacheng Du, Hongyang Niyato, Dusit Liu, Jiangchuan Leung, Victor C.M. College of Computer Science and Technology Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong School of Computing Science Simon Fraser University BurnabyBCV5A 1S6 Canada R&D Department Jiangxing Intelligence Inc. Nanjing210000 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518115 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering The University of British Columbia VancouverV6T 1Z4 Canada

the emergence of space-air-ground integrated multi-access edge computing (sAGiMEC) networks opens a significant opportunity for the rapidly growing low altitude economy (LAE), facilitating the development of various applications by offering efficient communication and computing services. However, the heterogeneous nature of sAGiMEC networks, coupled with the stringent computational and communication requirements of diverse applications in the LAE, introduces considerable challenges in integrating sAGiMEC into the LAE. in this work, we first present a digital twin-assisted sAGiMEC paradigm for LAE, where digital twin enables reliable network monitoring and management, while sAGiMEC provides efficient computing offloading services for internet of things sensor devices (isDs). then, a joi.t.satellite selection, computation offloading, communication resource allocation, computation resource allocation and UAV trajectory control optimization problem (JsC4OP) is formulated to maximize the quality of service (Qos) of isDs. Given the complexity of JsC4OP, we propose an online decentralized optimization approach (ODOA) to address the problem. specifically, JsC4OP is first transformed into a real-time decision-making optimization problem (RDOP) by leveraging Lyapunov optimization. then, to solve the RDOP, we introduce an online learning-based latency prediction method to predict the uncertain system environment and a game theoretic decision-making method to make real-time decisions. Finally, theoretical analysis confirms the effectiveness of the ODOA, while the simulation results demonstrate that the proposed ODOA outperforms other alternative approaches in terms of overall system performance. Copyright © 2024, the Authors. All rights reserved.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

innovations in Voice Navigation Using Object Detection to Empower the Visually impaired

Innovations in Voice Navigation Using Object Detection to Em...

引用

smart Generation Computing, Communication and Networking (sMARt GENCON), international Conference on

作者： Ranjeet suryawanshi Annepu Arudra Dankan Gowda V Mathu Uthaman swathi Pai M VK satya Prasad Department of Electronics and Telecommunications Engineering Bharati Vidyapeeth's college of Engineering Kolhapur Maharashtra India Department of Computer Science & Engineering Rajiv Gandhi Institute of Technology R T Nagar Cholanagar Bangalore Karnataka India Department of Electronics & Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka India Department of Computer Science and Engineering Mahaguru Institute of Technology Kattachira Kayamkulam Alappuzha India Department of Artificial intelligence and machine learning NMAM Institute of Technology Nitte Karnataka India Symbiosis Institute of Business Management Hyderabad Symbiosis International (Deemed University) Pune India

the project focuses on addressing the challenges faced by visually impaired individuals in navigating environments, especially when encountering obstacles or misplacing essential tools like walking sticks. A novel solution is proposed: a voice-controlled smart stick, designed to enhance the autonomy of visually impaired people in their daily activities without reliance on others. this research introduces a sophisticated walking stick equipped with ultrasonic sensors, operated via voice commands for ease of use and accessibility the voice-controlled smart stick is distinguished by its user-friendly interface, rapid responsiveness, minimal power consumption, lightweight design, and ease of folding and handling. this project not only offers a practical solution for the visually impaired but also signifies a significant advancement in assistive technology, enhancing independence and safety in daily life.

关键词：

来源：评论

学校读者我要写书评

暂无评论

innovative Method for Earthquake Prediction system using Hybrid Convolutional Neural Network and sVM

Innovative Method for Earthquake Prediction System using Hyb...

引用

2023 international Conference on Artificial intelligence and Applications, iCAiA 2023 and Alliance technology Conference, AtCON-1 2023

作者： Rajkumar, N. Kanimozhi, N. saravanakumar, P. Koneru, sireesha sapra, Puneet Rastogi, Ravi Vel Tech R. Dr.S. R&d I.S.T. Vel Tech Nagar Department of Cse Tamilnadu Chennai India School of Computing Srm Institute of Science and Technology Department of C.I Tamilnadu Chennai India Sri Krishna College of Engg. and Techn Department of C.E Tamilnadu Coimbatore India Koneru Lakshmaiah Edu.Foundation Department of Mechanical Engineering Andhra Pradesh Guntur India Rayat Bahra University Department of Cse Punjab Mohali India Nielit Uttar Pradesh Gorakhpur India

ISBN: (纸本)9781665456272

the ability to estimate casualties from earthquakes is crucial for effective disaster response. Conventional forecasting techniques have stringent sample data requirements and several parameters that must be manually specified, which can lead to subpar outcomes with prediction accuracy as low and a slow rate of learning. in the suggested hybrid model, CNN is employed as an automatic feature extractor, while sVM is used as a binary classifier. traditional CNN's completely linked layers are swapped out for a support vector machine in this model to improve prediction accuracy. this proposed approach employs CNN for automatic feature extraction, and an sVM classifier for automatic classification. the experimental findings showed that compared to the CNN model (89%), our hybrid model was significantly more accurate at 98.5% © 2023 iEEE.

关键词： support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Cloud-Based UV Monitoring system for Remote Real-time UV Exposure tracking

A Cloud-Based UV Monitoring System for Remote Real-Time UV E...

引用

smart Electronics and Communication (iCOsEC), international Conference on

作者： Dankan Gowda V V Nuthan Prasad KDV Prasad VK satya Prasad Yogesh Mahajan sampathirao suneetha Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka India Department of Electronics and Communication Engineering M S R I T Bangalore Karnataka India Symbiosis Institute of Business Management Hyderabad Symbiosis International (Deemed University) Pune India Symbiosis Centre for Management & Human Resource Development Symbiosis International University Pune Maharashtra India Department of Computer Science & Systems Engineering Andhra University College of Engineering Andhra University Visakhapatnam Andhra Pradesh India

Due to the widespread nature of sun-related health risks, sophisticated UV monitoring systems are urgently needed. this research study introduces a cloud-based UV monitoring system with the intent of remotely tracking and analyzing UV exposure in real time. the system incorporates a network of UV sensors deployed in various locations, continuously collecting UV radiation data. these sensors are linked to a cloud system, which allows for easy sharing and processing of collected data. As a result, we're working to perfect a cutting-edge device that can monitor vitamin D absorption, measure cumulative UV exposure, and warn of impending danger. Extensive studies have demonstrated the benefits of UV exposure for both general health and protection against the newly discovered coronavirus. However, finding a happy medium is important because too much sun exposure can cause cancer, lupus flares, and cataracts. the proposed model gives users the ability to set their own daily UV exposure limits, taking into account clinically validated thresholds for various skin tones. the developed sensor module is able to measure the UV index with high precision even in bright sunlight because it closely mimics the skin erythema spectrum.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An innovative Method for Paddy Yield Prediction Based on DCNN-ELM Approach

An Innovative Method for Paddy Yield Prediction Based on DCN...

引用

intelligent Data Communication technologies and internet of things (iDCiot), international Conference on

作者： Mohd. Asif Gandhi Lakhwinder singh Prabakaran V G. Bhupal Raj sowmiya Harshal Patil Department of Mechanical Engineering Anjuman-I-Islam's Kalsekar Technical Campus Affiliated to University of Mumbai Panvel India Department of Geography Lovely Professional University Phagwara India Department of Management Studies SNS College of Technology Coimbatore Tamil Nadu India School of Agriculture SR University Warangal India Department of CSE Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Maharashtra India

the majority of a country's population relies on agriculture for their livelihood. Water shortage, uncertainty in market prices due to supply and demand, erratic weather, and inaccurate crop predictions are just some of the new realities that farmers must adjust to. Environmental conditions, management tactics, crop genotype, and yield all interact in complex ways, making crop yield prediction difficult. this is especially true for paddy cultivation. Researchers utilize to forecasting the paddy yield through statistical methods, yet they failed to obtain greater precision due to several causes. Within the suggested methods, preprocessing, feature selection, and model training are all included. they employ adaptive data cleaning and denoising auto encoder in data preprocessing. All of the missing values in the input dataset are filled in using the pre-processing technique. they employ feature selection the CFs procedure uses statistical measurements as evaluation criteria to determine the quality of feature subsets. DCNN-ELM trains the models after the attributes are gathered. Compared to the DCNN and ELM techniques, the suggested strategy yields significantly better results. At 96.33 percent, this technique has an incredibly high probability of success.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：